/ ディレクトリ / プレイグラウンド / Skill_Seekers
● コミュニティ yusufkaraaslan ⚡ 即起動

Skill_Seekers

作者 yusufkaraaslan · yusufkaraaslan/Skill_Seekers

Turns docs sites, GitHub repos, PDFs, and videos into ready-to-use SKILL.md bundles — a factory for making new Claude skills.

Skill Seekers is a meta-skill: you point it at a documentation source and it produces a production-grade SKILL.md (500+ lines with examples) plus a references folder. It detects conflicts between documented APIs and real code, supports 18 source types, and exports to Claude Code, Cursor, Windsurf, LangChain, and vector DBs.

なぜ使うのか

主な機能

ライブデモ

実際の動作

skill-seekers-skill.replay ▶ 準備完了
0/0

インストール

クライアントを選択

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "skill-seekers-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/yusufkaraaslan/Skill_Seekers",
        "~/.claude/skills/Skill_Seekers"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config を開く。保存後、アプリを再起動。

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "skill-seekers-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/yusufkaraaslan/Skill_Seekers",
        "~/.claude/skills/Skill_Seekers"
      ],
      "_inferred": true
    }
  }
}

Cursor は Claude Desktop と同じ mcpServers スキーマを使用。プロジェクト設定はグローバルより優先。

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "skill-seekers-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/yusufkaraaslan/Skill_Seekers",
        "~/.claude/skills/Skill_Seekers"
      ],
      "_inferred": true
    }
  }
}

Cline サイドバーの MCP Servers アイコンをクリックし、"Edit Configuration" を選択。

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "skill-seekers-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/yusufkaraaslan/Skill_Seekers",
        "~/.claude/skills/Skill_Seekers"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop と同じ形式。Windsurf を再起動して反映。

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "skill-seekers-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/yusufkaraaslan/Skill_Seekers",
        "~/.claude/skills/Skill_Seekers"
      ]
    }
  ]
}

Continue はマップではなくサーバーオブジェクトの配列を使用。

~/.config/zed/settings.json
{
  "context_servers": {
    "skill-seekers-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/yusufkaraaslan/Skill_Seekers",
          "~/.claude/skills/Skill_Seekers"
        ]
      }
    }
  }
}

context_servers に追加。保存時に Zed がホットリロード。

claude mcp add skill-seekers-skill -- git clone https://github.com/yusufkaraaslan/Skill_Seekers ~/.claude/skills/Skill_Seekers

ワンライナー。claude mcp list で確認、claude mcp remove で削除。

ユースケース

実用的な使い方: Skill_Seekers

Turn a library's documentation site into a Claude skill in 10 minutes

👤 Developers who rely on a library Claude doesn't know well ⏱ ~15 min intermediate

使うタイミング: Claude keeps inventing function signatures for your favorite library because its training data is stale.

前提条件
  • URL of the library's docs site — The canonical ReadTheDocs, Docusaurus, or mintlify URL
フロー
  1. Point the skill at the docs
    Use skill-seekers to build a SKILL.md for https://docs.example.com. Output to ~/.claude/skills/example/.✓ コピーしました
    → Ingest phase reports page count and starts scraping
  2. Review the generated SKILL.md
    Show me the frontmatter and the first 50 lines of the generated SKILL.md.✓ コピーしました
    → Valid YAML frontmatter, clear sections
  3. Test with a real prompt
    Now use the new example skill to do <representative task>.✓ コピーしました
    → Claude uses real API names, not hallucinated ones

結果: A new skill in your ~/.claude/skills/ folder that Claude picks up automatically.

注意点
  • Docs-vs-code drift sneaks into the output — Let the conflict detector flag mismatches; skim the conflicts.md report it produces
組み合わせ: firecrawl · filesystem

Generate a skill directly from a GitHub repo's code and README

👤 Anyone onboarding Claude onto an internal or obscure OSS codebase ⏱ ~20 min intermediate

使うタイミング: No hosted docs exist — the README and the source are the only truth.

フロー
  1. Run on the repo URL
    Run skill-seekers on github.com/acme/internal-sdk, include code examples from tests/.✓ コピーしました
    → Extracts public API surface + example usage
  2. Iterate on the skill
    The first draft misses the auth flow — add a section on token setup.✓ コピーしました
    → SKILL.md expanded with that section

結果: A targeted skill Claude can invoke when working in that codebase.

注意点
  • Repo is huge and scraping stalls — Use excludePaths to skip vendored directories and test fixtures
組み合わせ: github

組み合わせ

他のMCPと組み合わせて10倍の力を

skill-seekers-skill + firecrawl

Firecrawl does the heavy JS-rendered scraping; Skill Seekers does the structuring

Use firecrawl to crawl the docs site, then skill-seekers to turn the output into a SKILL.md.✓ コピーしました
skill-seekers-skill + github

Pull repo contents via GitHub MCP, enhance into a skill

Fetch the acme/sdk repo's README, examples/, and types, then build a skill from them.✓ コピーしました

ツール

このMCPが提供する機能

ツール入力呼び出すタイミングコスト
Ingest source URL / repo / PDF path First phase — gather source material Free (plus any scraper API if used)
Enhance ingested content, target platform Second phase — AI-write the skill LLM tokens for enhancement
Conflict-detect docs + code sources Whenever you ingest both docs and source 0
Export target platform (Claude, Cursor, LangChain, etc.) Third phase — package for destination 0

コストと制限

運用コスト

APIクォータ
None for the skill itself; depends on which scraper you pair with
呼び出しあたりのトークン
Generation phase can use 10-50k tokens for a large library
金額
Free — the skill itself. Pairing scrapers (Firecrawl) may cost credits.
ヒント
Cache ingested content; re-run enhance/export without re-scraping.

セキュリティ

権限、シークレット、影響範囲

認証情報の保管: No credentials in the skill. Paired scrapers may need their own API keys.
データ送信先: Only to the sources you point it at

トラブルシューティング

よくあるエラーと対処法

Generated SKILL.md has placeholder sections

Source was too thin — re-run with more inputs (add the GitHub repo alongside the docs site).

Checkpoint resume starts over

Make sure you're running from the same working directory where the .skillseekers/ cache was created.

確認: ls .skillseekers/
Output skill isn't being invoked by Claude

Check the SKILL.md frontmatter's description field — Claude's auto-invocation depends on it matching the user prompt.

確認: head -20 ~/.claude/skills/<name>/SKILL.md

代替案

Skill_Seekers 他との比較

代替案代わりに使う場面トレードオフ
skillforgeYou want an interactive skill router that also creates skills on demandLighter generator; Skill Seekers is more thorough on heavy doc sources
Manual SKILL.md writingThe skill is small and you know the library coldFaster for trivial skills; tedious at scale

その他

リソース

📖 GitHub の公式 README を読む

🐙 オープンな issue を見る

🔍 400以上のMCPサーバーとSkillsを見る